Claude Fable 5 (xHigh): benchmark results
Provider: Anthropic. Released 2026-06-09. Access: API.
Aggregate Rating 1908 ± 21, rank #39 of 2170 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Terminal-Bench 2.1 (Best Reported Harness) | 83.82 | Score (%) | 100 |
| ARC-AGI-1 | 98.5 | Accuracy (%) | 98.4 |
| Conceptual Reasoning Index - Decision Theory (DTBench) | 95.55 | Chance-Corrected Score (0-100) | 95.7 |
| Epoch AI - Dtbench | 97.33 | Score | 95.1 |
| SimpleQA Verified | 70.7 | Accuracy (%) | 93.9 |
| LiveBench | 78.57 | LiveBench average (imported) | 93.6 |
| ARC-AGI-2 | 88.33 | Accuracy (%) | 92.6 |
| ReactBench | 42.1 | Pass@1 (%) | 92.3 |
| Conceptual Reasoning Index - Consistency (ACCoRD) | 81.9 | Chance-Corrected Score (0-100) | 91.9 |
| SEAL - SWE Atlas - Test Writing | 55.6 | Score | 90.5 |
| Conceptual Reasoning Index - Argument Evaluation (LMCA) | 61.02 | Chance-Corrected Score (0-100) | 88 |
| SEAL - SWE Atlas - Refactoring | 54.76 | Score | 87.5 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-xhigh · How It Works · Data refreshed daily, snapshot 2026-11-05.